INDEX

Explanations

intervals and mathematical notation

The neuron is triggered by numeric tokens (i.e. numbers) in the text.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

);

-1.81

and

-1.75

-1.68

We

-1.67

-1.54

is

-1.53

-1.49

}{

-1.48

Now

-1.46

 (‘

-1.41

POSITIVE LOGITS

蹰

1.73

 ſont

1.59

mlu

1.45

щие

1.41

 jednej

1.40

賸

1.39

 lesquels

1.38

 PRIZE

1.38

 allemand

1.38

 própri

1.38

Activations Density 0.012%